Cura 1T: A Dedicated LLM for Medical Agents
actAVA AI · hf · 2026-07-20
To address the complex communication, clinical reasoning, and workflow execution demands of the healthcare sector, actAVA AI has released the specialized LLM Cura 1T. The model is capable of handling patient consultations, image-text clinical reasoning, interactive diagnosis, and EHR (Electronic Health Record) tool calling.
Technical Highlights:
- Human-in-the-loop Self-evolution Cycle: Model training incorporates an agentic planning mechanism. In each evolution round, the training Agent plans target capabilities, trains the model, evaluates benchmark trajectories, and optimizes data mixture ratios based on observed failures.
- Precision Data-Driven: Capabilities are enhanced through targeted synthetic data and curated examples, avoiding the task degradation often caused by updating with generic medical data.
- Performance: In medical evaluation suites, Cura 1T ranks among frontier models while remaining competitive on out-of-domain reasoning and general agent benchmarks.
Related event: actAVA AI Launches Cura, a 1T-Parameter Medical Agent Model(2 posts)→
More from Models
- Kimi K2.8 Preview rolls out: near-K3 coding performance, 1M context for all tiers — teortaxesTex · 2026-09-11
- Looking for a classifier of software engineering task shapes to pick models per task — StewartalsopIII · 2026-09-11
- DeepSeek V4 Pro API to continue after Sept 2026, billing unchanged — teortaxesTex · 2026-09-11
- DeepSeek V4.1 Flash Hits 98% of GPT-6 Astra's Score at 1.4% of the Cost in Third-Party Benchmark — ayushtweetshere · 2026-09-11
- TheZvi Polls: Has Your Coding Model Choice Changed Since Fable 5.1 and Astra? — TheZvi · 2026-09-11
- antirez Weighs In on Anthropic Banning Minors From Using Claude — antirez · 2026-09-11